Model-Free Inference of Investor Preferences: A Relative Entropy IRL Approach
On the map: Offline RL and imitation learning from data → Inverse reinforcement learning
Abstract (arXiv)
We present a framework using Relative Entropy Inverse Reinforcement Learning (RE-IRL) to recover investor reward functions from observed investment actions and market conditions. Unlike traditional IRL algorithms, RE-IRL is employed to account for environments where transition probabilities are unknown or inaccessible. To address the challenge of data sparsity, we utilize a K-nearest neighbor approach to estimate the observed behavior policy. Furthermore, we propose a statistical testing framework to evaluate the validity and robustness of the estimated results.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 1 of its 7 references that are in the map. First posted on arXiv 27 Apr 2026.
Builds on
1 of 7 references.
References · 1
- 2021Convex optimizationcited by 2,479
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2022Combining Reinforcement Learning and Inverse Reinforcement Learning for Asset Allocation Recommendations
- 2020Revisiting Maximum Entropy Inverse Reinforcement Learning: New Perspectives and Algorithms
- 2026A Lecture Note on Offline RL and IRL, Part II: Foundations of Inverse Reinforcement Learning and Dynamic Discrete Choice Models
- 2019Generalized Maximum Causal Entropy for Inverse Reinforcement Learning
- 2021Inverse Reinforcement Learning with Explicit Policy Estimates
- 2025Statistical analysis of Inverse Entropy-regularized Reinforcement Learning
- 2024Convergence of a model-free entropy-regularized inverse reinforcement learning algorithm
- 2025Inverse Reinforcement Learning using Revealed Preferences and Passive Stochastic Optimization